Abstract
End-to-end Speech Translation (E2E ST) aims to directly translate source speech into target text. Existing ST methods perform poorly when only extremely small speech-text data are available for training. We observe that an ST model’s performance closely correlates with its embedding similarity between speech and source transcript. In this paper, we propose Word-Aligned COntrastive learning (WACO), a simple and effective method for extremely low-resource speech-to-text translation. Our key idea is bridging word-level representations for both speech and text modalities via contrastive learning. We evaluate WACO and other methods on the MuST-C dataset, a widely used ST benchmark, and on a low-resource direction Maltese-English from IWSLT 2023. Our experiments demonstrate that WACO outperforms the best baseline by 9+ BLEU points with only 1-hour parallel ST data. Code is available at https://github.com/owaski/WACO.- Anthology ID:
- 2023.acl-long.216
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3891–3907
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.216
- DOI:
- 10.18653/v1/2023.acl-long.216
- Cite (ACL):
- Siqi Ouyang, Rong Ye, and Lei Li. 2023. WACO: Word-Aligned Contrastive Learning for Speech Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3891–3907, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- WACO: Word-Aligned Contrastive Learning for Speech Translation (Ouyang et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.acl-long.216.pdf